Cereal yield (kg per hectare)

                    
# Check and install required packages
required_packages <- c("WDI", "countrycode", "dplyr")

for (pkg in required_packages) {
  if (!requireNamespace(pkg, quietly = TRUE)) {
    install.packages(pkg)
  }
}

# Load the necessary libraries
library(WDI)
library(dplyr)
library(countrycode)

# Define the dataset code (World Bank indicator code)
dataset_code <- 'AG.YLD.CREL.KG'

# Download data using WDI package
dat <- WDI(indicator = dataset_code)

# Filter only countries using 'is_country' from countrycode
# This uses iso2c to identify whether the entry is a recognized country
dat <- dat %>%
  filter(countrycode(iso2c, origin = 'iso2c', destination = 'country.name', warn = FALSE) %in%
           countrycode::codelist$country.name.en)

# Ensure dataset is ordered by country and year
dat <- dat %>%
  arrange(iso3c, year)

# Rename the dataset_code column to "value" for easier manipulation
dat <- dat %>%
  rename(value = !!dataset_code)

# Calculate year-over-year (YoY) change and percentage change
dat <- dat %>%
  group_by(iso3c) %>%
  mutate(
    value_change = value - lag(value),                              # Absolute change from previous year
    value_change_percent = 100 * (value - lag(value)) / lag(value) # Percent change from previous year
  ) %>%
  ungroup()

# Calculate rank by year (higher value => higher rank)
dat <- dat %>%
  group_by(year) %>%
  mutate(rank = dense_rank(desc(value))) %>% # Rank countries by descending value
  ungroup()

# Calculate rank change (positive = moved up, negative = moved down)
dat <- dat %>%
  group_by(iso3c) %>%
  mutate(rank_change = rank - lag(rank)) %>% # Change in rank compared to previous year
  ungroup()

# Select and reorder final columns
final_data <- dat %>%
  select(
    country,
    iso2c,
    iso3c,
    year,
    value,
    value_change,
    value_change_percent,
    rank,
    rank_change
  )

# Add labels (variable descriptions)
attr(final_data$country, "label") <- "Country name"
attr(final_data$iso2c, "label") <- "ISO 2-letter country code"
attr(final_data$iso3c, "label") <- "ISO 3-letter country code"
attr(final_data$year, "label") <- "Year"
attr(final_data$value, "label") <- "GDP per capita (current US$)"
attr(final_data$value_change, "label") <- "Year-over-Year change in value"
attr(final_data$value_change_percent, "label") <- "Year-over-Year percent change in value"
attr(final_data$rank, "label") <- "Country rank by GDP per capita (higher = richer)"
attr(final_data$rank_change, "label") <- "Change in rank from previous year"

# Print the first few rows of the final dataset
print(head(final_data, 10))